tungsten-logo
Sign In
Samurai Girl with Light & Shadow
light-and-shadow:v1.0
evevalentine2017
evevalentine2017
·
12/17/2023
366
Input
prompt
Specify things to see in the output
martial, 1girl, solo, simple background, outstretched arm, Jumping, (yellow hanfu dress: 1.4), (Ancient Chinese sword, holding sword: 1.2), illustration style, Chinese martial arts war scenes, Chinese ink style, martial arts style, (medium breasts: 1.3), long sleeves, Chinese clothes, (glowing: 1.4), splashing, fighting stance, Chinese calligraphy, ink painting, characters, calligraphy characters, text background, (full body: 1.2), <lora:FaceBeauty_qinglong_V3:1>
negative_prompt
Specify things to not see in the output
(nsfw:1.3), bad_prompt_version2-neg, bad-hands-5 , EasyNegative V2, (worst quality:2), (low quality:2), (normal quality:2), lowres, watermark, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature,
num_outputs
Number of output images
4
width
Output image width
768
height
Output image height
768
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
saturation
Adjust saturation
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
498398700
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
0.55
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
1
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
1
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
1
sampler
Sampler type
DPM++ 3M SDE Karras
samping_steps
Number of denoising steps
55
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
blessed2_fp16.safetensors
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
FaceBeauty_qinglong_V3.safetensors
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
bad_prompt_version2-neg.pt
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
EasyNegativeV2.safetensors
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
bad-hands-5.pt
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
Output
https://files.tungsten.run/uploads/5cdf27f197424b1dbf4c3a564a85f914/00000-498398700.webp
https://files.tungsten.run/uploads/439cef4cb54e4984b86495c6ca665ed7/00001-498398701.webp
https://files.tungsten.run/uploads/b6e11499a9984c5a849a5d7473dc3cd2/00002-498398702.webp
https://files.tungsten.run/uploads/1703c44dc1704ce4be0de2b85ae8d8a0/00003-498398703.webp
Finished in 150.8 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: martial, 1girl, solo, simple background, outstretched arm, Jumping, (yellow hanfu dress: 1.4), (Ancient Chinese sword, holding sword: 1.2), illustration style, Chinese martial arts war scenes, Chinese ink style, martial arts style, (medium breasts: 1.3), long sleeves, Chinese clothes, (glowing: 1.4), splashing, fighting stance, Chinese calligraphy, ink painting, characters, calligraphy characters, text background, (full body: 1.2), <lora:FaceBeauty_qinglong_V3:1> Full negative prompt: (nsfw:1.3), bad_prompt_version2-neg, bad-hands-5 , EasyNegative V2, (worst quality:2), (low quality:2), (normal quality:2), lowres, watermark, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, 0%| | 0/55 [00:00<?, ?it/s] 2%|▏ | 1/55 [00:01<01:43, 1.91s/it] 4%|▎ | 2/55 [00:03<01:37, 1.84s/it] 5%|▌ | 3/55 [00:05<01:36, 1.86s/it] 7%|▋ | 4/55 [00:07<01:36, 1.89s/it] 9%|▉ | 5/55 [00:09<01:33, 1.88s/it] 11%|█ | 6/55 [00:11<01:29, 1.83s/it] 13%|█▎ | 7/55 [00:12<01:25, 1.79s/it] 15%|█▍ | 8/55 [00:14<01:25, 1.82s/it] 16%|█▋ | 9/55 [00:16<01:24, 1.83s/it] 18%|█▊ | 10/55 [00:18<01:21, 1.82s/it] 20%|██ | 11/55 [00:20<01:20, 1.82s/it] 22%|██▏ | 12/55 [00:21<01:15, 1.76s/it] 24%|██▎ | 13/55 [00:23<01:14, 1.76s/it] 25%|██▌ | 14/55 [00:25<01:10, 1.72s/it] 27%|██▋ | 15/55 [00:26<01:09, 1.73s/it] 29%|██▉ | 16/55 [00:28<01:07, 1.74s/it] 31%|███ | 17/55 [00:30<01:07, 1.76s/it] 33%|███▎ | 18/55 [00:32<01:03, 1.73s/it] 35%|███▍ | 19/55 [00:33<01:02, 1.73s/it] 36%|███▋ | 20/55 [00:35<01:02, 1.79s/it] 38%|███▊ | 21/55 [00:37<01:00, 1.77s/it] 40%|████ | 22/55 [00:39<00:58, 1.78s/it] 42%|████▏ | 23/55 [00:40<00:55, 1.73s/it] 44%|████▎ | 24/55 [00:42<00:53, 1.72s/it] 45%|████▌ | 25/55 [00:44<00:51, 1.72s/it] 47%|████▋ | 26/55 [00:46<00:50, 1.75s/it] 49%|████▉ | 27/55 [00:47<00:48, 1.73s/it] 51%|█████ | 28/55 [00:49<00:45, 1.70s/it] 53%|█████▎ | 29/55 [00:51<00:44, 1.71s/it] 55%|█████▍ | 30/55 [00:52<00:42, 1.68s/it] 56%|█████▋ | 31/55 [00:54<00:40, 1.69s/it] 58%|█████▊ | 32/55 [00:56<00:38, 1.68s/it] 60%|██████ | 33/55 [00:57<00:37, 1.70s/it] 62%|██████▏ | 34/55 [00:59<00:35, 1.68s/it] 64%|██████▎ | 35/55 [01:01<00:33, 1.68s/it] 65%|██████▌ | 36/55 [01:03<00:32, 1.72s/it] 67%|██████▋ | 37/55 [01:04<00:30, 1.71s/it] 69%|██████▉ | 38/55 [01:06<00:27, 1.64s/it] 71%|███████ | 39/55 [01:07<00:25, 1.57s/it] 73%|███████▎ | 40/55 [01:09<00:23, 1.54s/it] 75%|███████▍ | 41/55 [01:10<00:21, 1.56s/it] 76%|███████▋ | 42/55 [01:12<00:20, 1.61s/it] 78%|███████▊ | 43/55 [01:14<00:19, 1.61s/it] 80%|████████ | 44/55 [01:15<00:17, 1.58s/it] 82%|████████▏ | 45/55 [01:17<00:15, 1.58s/it] 84%|████████▎ | 46/55 [01:18<00:14, 1.62s/it] 85%|████████▌ | 47/55 [01:20<00:12, 1.60s/it] 87%|████████▋ | 48/55 [01:21<00:10, 1.56s/it] 89%|████████▉ | 49/55 [01:23<00:09, 1.63s/it] 91%|█████████ | 50/55 [01:25<00:07, 1.54s/it] 93%|█████████▎| 51/55 [01:26<00:05, 1.46s/it] 95%|█████████▍| 52/55 [01:27<00:04, 1.45s/it] 96%|█████████▋| 53/55 [01:29<00:02, 1.43s/it] 98%|█████████▊| 54/55 [01:29<00:01, 1.24s/it] 100%|██████████| 55/55 [01:30<00:00, 1.06s/it] 100%|██████████| 55/55 [01:30<00:00, 1.65s/it] Decoding latents in cuda:0... done in 0.98s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.7ms Speed: 4.3ms preprocess, 7.7ms inference, 28.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:00<00:17, 1.76it/s] 6%|▋ | 2/31 [00:00<00:14, 2.05it/s] 10%|▉ | 3/31 [00:01<00:12, 2.23it/s] 13%|█▎ | 4/31 [00:01<00:11, 2.34it/s] 16%|█▌ | 5/31 [00:02<00:10, 2.37it/s] 19%|█▉ | 6/31 [00:02<00:10, 2.44it/s] 23%|██▎ | 7/31 [00:03<00:09, 2.44it/s] 26%|██▌ | 8/31 [00:03<00:09, 2.46it/s] 29%|██▉ | 9/31 [00:03<00:09, 2.41it/s] 32%|███▏ | 10/31 [00:04<00:08, 2.47it/s] 35%|███▌ | 11/31 [00:04<00:08, 2.47it/s] 39%|███▊ | 12/31 [00:05<00:07, 2.43it/s] 42%|████▏ | 13/31 [00:05<00:07, 2.46it/s] 45%|████▌ | 14/31 [00:05<00:06, 2.57it/s] 48%|████▊ | 15/31 [00:06<00:05, 2.71it/s] 52%|█████▏ | 16/31 [00:06<00:05, 2.77it/s] 55%|█████▍ | 17/31 [00:06<00:05, 2.73it/s] 58%|█████▊ | 18/31 [00:07<00:04, 2.64it/s] 61%|██████▏ | 19/31 [00:07<00:04, 2.64it/s] 65%|██████▍ | 20/31 [00:07<00:04, 2.66it/s] 68%|██████▊ | 21/31 [00:08<00:03, 2.67it/s] 71%|███████ | 22/31 [00:08<00:03, 2.57it/s] 74%|███████▍ | 23/31 [00:09<00:03, 2.62it/s] 77%|███████▋ | 24/31 [00:09<00:02, 2.69it/s] 81%|████████ | 25/31 [00:09<00:02, 2.59it/s] 84%|████████▍ | 26/31 [00:10<00:01, 2.74it/s] 87%|████████▋ | 27/31 [00:10<00:01, 2.87it/s] 90%|█████████ | 28/31 [00:10<00:01, 2.88it/s] 94%|█████████▎| 29/31 [00:11<00:00, 2.91it/s] 97%|█████████▋| 30/31 [00:11<00:00, 3.40it/s] 100%|██████████| 31/31 [00:11<00:00, 4.00it/s] 100%|██████████| 31/31 [00:11<00:00, 2.68it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 3.1ms preprocess, 7.4ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:00<00:12, 2.43it/s] 6%|▋ | 2/31 [00:00<00:12, 2.40it/s] 10%|▉ | 3/31 [00:01<00:11, 2.44it/s] 13%|█▎ | 4/31 [00:01<00:10, 2.52it/s] 16%|█▌ | 5/31 [00:02<00:10, 2.49it/s] 19%|█▉ | 6/31 [00:02<00:09, 2.52it/s] 23%|██▎ | 7/31 [00:02<00:09, 2.51it/s] 26%|██▌ | 8/31 [00:03<00:09, 2.52it/s] 29%|██▉ | 9/31 [00:03<00:08, 2.50it/s] 32%|███▏ | 10/31 [00:03<00:08, 2.54it/s] 35%|███▌ | 11/31 [00:04<00:07, 2.53it/s] 39%|███▊ | 12/31 [00:04<00:07, 2.48it/s] 42%|████▏ | 13/31 [00:05<00:07, 2.50it/s] 45%|████▌ | 14/31 [00:05<00:06, 2.61it/s] 48%|████▊ | 15/31 [00:05<00:05, 2.75it/s] 52%|█████▏ | 16/31 [00:06<00:05, 2.80it/s] 55%|█████▍ | 17/31 [00:06<00:05, 2.76it/s] 58%|█████▊ | 18/31 [00:06<00:04, 2.67it/s] 61%|██████▏ | 19/31 [00:07<00:04, 2.67it/s] 65%|██████▍ | 20/31 [00:07<00:04, 2.70it/s] 68%|██████▊ | 21/31 [00:08<00:03, 2.71it/s] 71%|███████ | 22/31 [00:08<00:03, 2.66it/s] 74%|███████▍ | 23/31 [00:08<00:02, 2.68it/s] 77%|███████▋ | 24/31 [00:09<00:02, 2.73it/s] 81%|████████ | 25/31 [00:09<00:02, 2.62it/s] 84%|████████▍ | 26/31 [00:09<00:01, 2.79it/s] 87%|████████▋ | 27/31 [00:10<00:01, 2.92it/s] 90%|█████████ | 28/31 [00:10<00:01, 2.94it/s] 94%|█████████▎| 29/31 [00:10<00:00, 2.98it/s] 97%|█████████▋| 30/31 [00:11<00:00, 3.46it/s] 100%|██████████| 31/31 [00:11<00:00, 4.06it/s] 100%|██████████| 31/31 [00:11<00:00, 2.77it/s] Decoding latents in cuda:0... =========================================== A tensor with all NaNs was produced in VAE. Converted VAE into 32-bit float and retry. =========================================== done in 0.44s Move latents to cpu... done in 0.23s 0: 640x640 1 face, 8.1ms Speed: 2.8ms preprocess, 8.1ms inference, 2.1ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:00<00:12, 2.31it/s] 6%|▋ | 2/31 [00:00<00:12, 2.28it/s] 10%|▉ | 3/31 [00:01<00:11, 2.35it/s] 13%|█▎ | 4/31 [00:01<00:11, 2.42it/s] 16%|█▌ | 5/31 [00:02<00:10, 2.41it/s] 19%|█▉ | 6/31 [00:02<00:10, 2.47it/s] 23%|██▎ | 7/31 [00:02<00:09, 2.47it/s] 26%|██▌ | 8/31 [00:03<00:09, 2.46it/s] 29%|██▉ | 9/31 [00:03<00:09, 2.43it/s] 32%|███▏ | 10/31 [00:04<00:08, 2.47it/s] 35%|███▌ | 11/31 [00:04<00:08, 2.45it/s] 39%|███▊ | 12/31 [00:04<00:07, 2.40it/s] 42%|████▏ | 13/31 [00:05<00:07, 2.43it/s] 45%|████▌ | 14/31 [00:05<00:06, 2.54it/s] 48%|████▊ | 15/31 [00:06<00:06, 2.66it/s] 52%|█████▏ | 16/31 [00:06<00:05, 2.73it/s] 55%|█████▍ | 17/31 [00:06<00:05, 2.71it/s] 58%|█████▊ | 18/31 [00:07<00:05, 2.60it/s] 61%|██████▏ | 19/31 [00:07<00:04, 2.62it/s] 65%|██████▍ | 20/31 [00:07<00:04, 2.66it/s] 68%|██████▊ | 21/31 [00:08<00:03, 2.67it/s] 71%|███████ | 22/31 [00:08<00:03, 2.58it/s] 74%|███████▍ | 23/31 [00:09<00:03, 2.60it/s] 77%|███████▋ | 24/31 [00:09<00:02, 2.65it/s] 81%|████████ | 25/31 [00:09<00:02, 2.53it/s] 84%|████████▍ | 26/31 [00:10<00:01, 2.69it/s] 87%|████████▋ | 27/31 [00:10<00:01, 2.83it/s] 90%|█████████ | 28/31 [00:10<00:01, 2.86it/s] 94%|█████████▎| 29/31 [00:11<00:00, 2.91it/s] 97%|█████████▋| 30/31 [00:11<00:00, 3.40it/s] 100%|██████████| 31/31 [00:11<00:00, 4.01it/s] 100%|██████████| 31/31 [00:11<00:00, 2.69it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 2.7ms preprocess, 7.4ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:00<00:12, 2.44it/s] 6%|▋ | 2/31 [00:00<00:12, 2.38it/s] 10%|▉ | 3/31 [00:01<00:11, 2.44it/s] 13%|█▎ | 4/31 [00:01<00:10, 2.51it/s] 16%|█▌ | 5/31 [00:02<00:10, 2.48it/s] 19%|█▉ | 6/31 [00:02<00:09, 2.54it/s] 23%|██▎ | 7/31 [00:02<00:09, 2.52it/s] 26%|██▌ | 8/31 [00:03<00:09, 2.53it/s] 29%|██▉ | 9/31 [00:03<00:08, 2.48it/s] 32%|███▏ | 10/31 [00:03<00:08, 2.53it/s] 35%|███▌ | 11/31 [00:04<00:07, 2.52it/s] 39%|███▊ | 12/31 [00:04<00:07, 2.47it/s] 42%|████▏ | 13/31 [00:05<00:07, 2.49it/s] 45%|████▌ | 14/31 [00:05<00:06, 2.59it/s] 48%|████▊ | 15/31 [00:05<00:05, 2.72it/s] 52%|█████▏ | 16/31 [00:06<00:05, 2.77it/s] 55%|█████▍ | 17/31 [00:06<00:05, 2.72it/s] 58%|█████▊ | 18/31 [00:07<00:04, 2.64it/s] 61%|██████▏ | 19/31 [00:07<00:04, 2.64it/s] 65%|██████▍ | 20/31 [00:07<00:04, 2.66it/s] 68%|██████▊ | 21/31 [00:08<00:03, 2.65it/s] 71%|███████ | 22/31 [00:08<00:03, 2.59it/s] 74%|███████▍ | 23/31 [00:08<00:03, 2.64it/s] 77%|███████▋ | 24/31 [00:09<00:02, 2.70it/s] 81%|████████ | 25/31 [00:09<00:02, 2.58it/s] 84%|████████▍ | 26/31 [00:10<00:01, 2.75it/s] 87%|████████▋ | 27/31 [00:10<00:01, 2.89it/s] 90%|█████████ | 28/31 [00:10<00:01, 2.90it/s] 94%|█████████▎| 29/31 [00:10<00:00, 2.95it/s] 97%|█████████▋| 30/31 [00:11<00:00, 3.44it/s] 100%|██████████| 31/31 [00:11<00:00, 4.05it/s] 100%|██████████| 31/31 [00:11<00:00, 2.74it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s Finished.
prompt
Specify things to see in the output
martial, 1girl, solo, simple background, outstretched arm, Jumping, (yellow hanfu dress: 1.4), (Ancient Chinese sword, holding sword: 1.2), illustration style, Chinese martial arts war scenes, Chinese ink style, martial arts style, (medium breasts: 1.3), long sleeves, Chinese clothes, (glowing: 1.4), splashing, fighting stance, Chinese calligraphy, ink painting, characters, calligraphy characters, text background, (full body: 1.2), <lora:FaceBeauty_qinglong_V3:1>
negative_prompt
Specify things to not see in the output
(nsfw:1.3), bad_prompt_version2-neg, bad-hands-5 , EasyNegative V2, (worst quality:2), (low quality:2), (normal quality:2), lowres, watermark, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature,
num_outputs
Number of output images
4
width
Output image width
768
height
Output image height
768
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
saturation
Adjust saturation
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
498398700
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
0.55
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
1
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
1
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
1
sampler
Sampler type
DPM++ 3M SDE Karras
samping_steps
Number of denoising steps
55
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
blessed2_fp16.safetensors
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
FaceBeauty_qinglong_V3.safetensors
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
bad_prompt_version2-neg.pt
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
EasyNegativeV2.safetensors
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
bad-hands-5.pt
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
https://files.tungsten.run/uploads/5cdf27f197424b1dbf4c3a564a85f914/00000-498398700.webp
https://files.tungsten.run/uploads/439cef4cb54e4984b86495c6ca665ed7/00001-498398701.webp
https://files.tungsten.run/uploads/b6e11499a9984c5a849a5d7473dc3cd2/00002-498398702.webp
https://files.tungsten.run/uploads/1703c44dc1704ce4be0de2b85ae8d8a0/00003-498398703.webp
Finished in 150.8 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: martial, 1girl, solo, simple background, outstretched arm, Jumping, (yellow hanfu dress: 1.4), (Ancient Chinese sword, holding sword: 1.2), illustration style, Chinese martial arts war scenes, Chinese ink style, martial arts style, (medium breasts: 1.3), long sleeves, Chinese clothes, (glowing: 1.4), splashing, fighting stance, Chinese calligraphy, ink painting, characters, calligraphy characters, text background, (full body: 1.2), <lora:FaceBeauty_qinglong_V3:1> Full negative prompt: (nsfw:1.3), bad_prompt_version2-neg, bad-hands-5 , EasyNegative V2, (worst quality:2), (low quality:2), (normal quality:2), lowres, watermark, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, 0%| | 0/55 [00:00<?, ?it/s] 2%|▏ | 1/55 [00:01<01:43, 1.91s/it] 4%|▎ | 2/55 [00:03<01:37, 1.84s/it] 5%|▌ | 3/55 [00:05<01:36, 1.86s/it] 7%|▋ | 4/55 [00:07<01:36, 1.89s/it] 9%|▉ | 5/55 [00:09<01:33, 1.88s/it] 11%|█ | 6/55 [00:11<01:29, 1.83s/it] 13%|█▎ | 7/55 [00:12<01:25, 1.79s/it] 15%|█▍ | 8/55 [00:14<01:25, 1.82s/it] 16%|█▋ | 9/55 [00:16<01:24, 1.83s/it] 18%|█▊ | 10/55 [00:18<01:21, 1.82s/it] 20%|██ | 11/55 [00:20<01:20, 1.82s/it] 22%|██▏ | 12/55 [00:21<01:15, 1.76s/it] 24%|██▎ | 13/55 [00:23<01:14, 1.76s/it] 25%|██▌ | 14/55 [00:25<01:10, 1.72s/it] 27%|██▋ | 15/55 [00:26<01:09, 1.73s/it] 29%|██▉ | 16/55 [00:28<01:07, 1.74s/it] 31%|███ | 17/55 [00:30<01:07, 1.76s/it] 33%|███▎ | 18/55 [00:32<01:03, 1.73s/it] 35%|███▍ | 19/55 [00:33<01:02, 1.73s/it] 36%|███▋ | 20/55 [00:35<01:02, 1.79s/it] 38%|███▊ | 21/55 [00:37<01:00, 1.77s/it] 40%|████ | 22/55 [00:39<00:58, 1.78s/it] 42%|████▏ | 23/55 [00:40<00:55, 1.73s/it] 44%|████▎ | 24/55 [00:42<00:53, 1.72s/it] 45%|████▌ | 25/55 [00:44<00:51, 1.72s/it] 47%|████▋ | 26/55 [00:46<00:50, 1.75s/it] 49%|████▉ | 27/55 [00:47<00:48, 1.73s/it] 51%|█████ | 28/55 [00:49<00:45, 1.70s/it] 53%|█████▎ | 29/55 [00:51<00:44, 1.71s/it] 55%|█████▍ | 30/55 [00:52<00:42, 1.68s/it] 56%|█████▋ | 31/55 [00:54<00:40, 1.69s/it] 58%|█████▊ | 32/55 [00:56<00:38, 1.68s/it] 60%|██████ | 33/55 [00:57<00:37, 1.70s/it] 62%|██████▏ | 34/55 [00:59<00:35, 1.68s/it] 64%|██████▎ | 35/55 [01:01<00:33, 1.68s/it] 65%|██████▌ | 36/55 [01:03<00:32, 1.72s/it] 67%|██████▋ | 37/55 [01:04<00:30, 1.71s/it] 69%|██████▉ | 38/55 [01:06<00:27, 1.64s/it] 71%|███████ | 39/55 [01:07<00:25, 1.57s/it] 73%|███████▎ | 40/55 [01:09<00:23, 1.54s/it] 75%|███████▍ | 41/55 [01:10<00:21, 1.56s/it] 76%|███████▋ | 42/55 [01:12<00:20, 1.61s/it] 78%|███████▊ | 43/55 [01:14<00:19, 1.61s/it] 80%|████████ | 44/55 [01:15<00:17, 1.58s/it] 82%|████████▏ | 45/55 [01:17<00:15, 1.58s/it] 84%|████████▎ | 46/55 [01:18<00:14, 1.62s/it] 85%|████████▌ | 47/55 [01:20<00:12, 1.60s/it] 87%|████████▋ | 48/55 [01:21<00:10, 1.56s/it] 89%|████████▉ | 49/55 [01:23<00:09, 1.63s/it] 91%|█████████ | 50/55 [01:25<00:07, 1.54s/it] 93%|█████████▎| 51/55 [01:26<00:05, 1.46s/it] 95%|█████████▍| 52/55 [01:27<00:04, 1.45s/it] 96%|█████████▋| 53/55 [01:29<00:02, 1.43s/it] 98%|█████████▊| 54/55 [01:29<00:01, 1.24s/it] 100%|██████████| 55/55 [01:30<00:00, 1.06s/it] 100%|██████████| 55/55 [01:30<00:00, 1.65s/it] Decoding latents in cuda:0... done in 0.98s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.7ms Speed: 4.3ms preprocess, 7.7ms inference, 28.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:00<00:17, 1.76it/s] 6%|▋ | 2/31 [00:00<00:14, 2.05it/s] 10%|▉ | 3/31 [00:01<00:12, 2.23it/s] 13%|█▎ | 4/31 [00:01<00:11, 2.34it/s] 16%|█▌ | 5/31 [00:02<00:10, 2.37it/s] 19%|█▉ | 6/31 [00:02<00:10, 2.44it/s] 23%|██▎ | 7/31 [00:03<00:09, 2.44it/s] 26%|██▌ | 8/31 [00:03<00:09, 2.46it/s] 29%|██▉ | 9/31 [00:03<00:09, 2.41it/s] 32%|███▏ | 10/31 [00:04<00:08, 2.47it/s] 35%|███▌ | 11/31 [00:04<00:08, 2.47it/s] 39%|███▊ | 12/31 [00:05<00:07, 2.43it/s] 42%|████▏ | 13/31 [00:05<00:07, 2.46it/s] 45%|████▌ | 14/31 [00:05<00:06, 2.57it/s] 48%|████▊ | 15/31 [00:06<00:05, 2.71it/s] 52%|█████▏ | 16/31 [00:06<00:05, 2.77it/s] 55%|█████▍ | 17/31 [00:06<00:05, 2.73it/s] 58%|█████▊ | 18/31 [00:07<00:04, 2.64it/s] 61%|██████▏ | 19/31 [00:07<00:04, 2.64it/s] 65%|██████▍ | 20/31 [00:07<00:04, 2.66it/s] 68%|██████▊ | 21/31 [00:08<00:03, 2.67it/s] 71%|███████ | 22/31 [00:08<00:03, 2.57it/s] 74%|███████▍ | 23/31 [00:09<00:03, 2.62it/s] 77%|███████▋ | 24/31 [00:09<00:02, 2.69it/s] 81%|████████ | 25/31 [00:09<00:02, 2.59it/s] 84%|████████▍ | 26/31 [00:10<00:01, 2.74it/s] 87%|████████▋ | 27/31 [00:10<00:01, 2.87it/s] 90%|█████████ | 28/31 [00:10<00:01, 2.88it/s] 94%|█████████▎| 29/31 [00:11<00:00, 2.91it/s] 97%|█████████▋| 30/31 [00:11<00:00, 3.40it/s] 100%|██████████| 31/31 [00:11<00:00, 4.00it/s] 100%|██████████| 31/31 [00:11<00:00, 2.68it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 3.1ms preprocess, 7.4ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:00<00:12, 2.43it/s] 6%|▋ | 2/31 [00:00<00:12, 2.40it/s] 10%|▉ | 3/31 [00:01<00:11, 2.44it/s] 13%|█▎ | 4/31 [00:01<00:10, 2.52it/s] 16%|█▌ | 5/31 [00:02<00:10, 2.49it/s] 19%|█▉ | 6/31 [00:02<00:09, 2.52it/s] 23%|██▎ | 7/31 [00:02<00:09, 2.51it/s] 26%|██▌ | 8/31 [00:03<00:09, 2.52it/s] 29%|██▉ | 9/31 [00:03<00:08, 2.50it/s] 32%|███▏ | 10/31 [00:03<00:08, 2.54it/s] 35%|███▌ | 11/31 [00:04<00:07, 2.53it/s] 39%|███▊ | 12/31 [00:04<00:07, 2.48it/s] 42%|████▏ | 13/31 [00:05<00:07, 2.50it/s] 45%|████▌ | 14/31 [00:05<00:06, 2.61it/s] 48%|████▊ | 15/31 [00:05<00:05, 2.75it/s] 52%|█████▏ | 16/31 [00:06<00:05, 2.80it/s] 55%|█████▍ | 17/31 [00:06<00:05, 2.76it/s] 58%|█████▊ | 18/31 [00:06<00:04, 2.67it/s] 61%|██████▏ | 19/31 [00:07<00:04, 2.67it/s] 65%|██████▍ | 20/31 [00:07<00:04, 2.70it/s] 68%|██████▊ | 21/31 [00:08<00:03, 2.71it/s] 71%|███████ | 22/31 [00:08<00:03, 2.66it/s] 74%|███████▍ | 23/31 [00:08<00:02, 2.68it/s] 77%|███████▋ | 24/31 [00:09<00:02, 2.73it/s] 81%|████████ | 25/31 [00:09<00:02, 2.62it/s] 84%|████████▍ | 26/31 [00:09<00:01, 2.79it/s] 87%|████████▋ | 27/31 [00:10<00:01, 2.92it/s] 90%|█████████ | 28/31 [00:10<00:01, 2.94it/s] 94%|█████████▎| 29/31 [00:10<00:00, 2.98it/s] 97%|█████████▋| 30/31 [00:11<00:00, 3.46it/s] 100%|██████████| 31/31 [00:11<00:00, 4.06it/s] 100%|██████████| 31/31 [00:11<00:00, 2.77it/s] Decoding latents in cuda:0... =========================================== A tensor with all NaNs was produced in VAE. Converted VAE into 32-bit float and retry. =========================================== done in 0.44s Move latents to cpu... done in 0.23s 0: 640x640 1 face, 8.1ms Speed: 2.8ms preprocess, 8.1ms inference, 2.1ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:00<00:12, 2.31it/s] 6%|▋ | 2/31 [00:00<00:12, 2.28it/s] 10%|▉ | 3/31 [00:01<00:11, 2.35it/s] 13%|█▎ | 4/31 [00:01<00:11, 2.42it/s] 16%|█▌ | 5/31 [00:02<00:10, 2.41it/s] 19%|█▉ | 6/31 [00:02<00:10, 2.47it/s] 23%|██▎ | 7/31 [00:02<00:09, 2.47it/s] 26%|██▌ | 8/31 [00:03<00:09, 2.46it/s] 29%|██▉ | 9/31 [00:03<00:09, 2.43it/s] 32%|███▏ | 10/31 [00:04<00:08, 2.47it/s] 35%|███▌ | 11/31 [00:04<00:08, 2.45it/s] 39%|███▊ | 12/31 [00:04<00:07, 2.40it/s] 42%|████▏ | 13/31 [00:05<00:07, 2.43it/s] 45%|████▌ | 14/31 [00:05<00:06, 2.54it/s] 48%|████▊ | 15/31 [00:06<00:06, 2.66it/s] 52%|█████▏ | 16/31 [00:06<00:05, 2.73it/s] 55%|█████▍ | 17/31 [00:06<00:05, 2.71it/s] 58%|█████▊ | 18/31 [00:07<00:05, 2.60it/s] 61%|██████▏ | 19/31 [00:07<00:04, 2.62it/s] 65%|██████▍ | 20/31 [00:07<00:04, 2.66it/s] 68%|██████▊ | 21/31 [00:08<00:03, 2.67it/s] 71%|███████ | 22/31 [00:08<00:03, 2.58it/s] 74%|███████▍ | 23/31 [00:09<00:03, 2.60it/s] 77%|███████▋ | 24/31 [00:09<00:02, 2.65it/s] 81%|████████ | 25/31 [00:09<00:02, 2.53it/s] 84%|████████▍ | 26/31 [00:10<00:01, 2.69it/s] 87%|████████▋ | 27/31 [00:10<00:01, 2.83it/s] 90%|█████████ | 28/31 [00:10<00:01, 2.86it/s] 94%|█████████▎| 29/31 [00:11<00:00, 2.91it/s] 97%|█████████▋| 30/31 [00:11<00:00, 3.40it/s] 100%|██████████| 31/31 [00:11<00:00, 4.01it/s] 100%|██████████| 31/31 [00:11<00:00, 2.69it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 2.7ms preprocess, 7.4ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:00<00:12, 2.44it/s] 6%|▋ | 2/31 [00:00<00:12, 2.38it/s] 10%|▉ | 3/31 [00:01<00:11, 2.44it/s] 13%|█▎ | 4/31 [00:01<00:10, 2.51it/s] 16%|█▌ | 5/31 [00:02<00:10, 2.48it/s] 19%|█▉ | 6/31 [00:02<00:09, 2.54it/s] 23%|██▎ | 7/31 [00:02<00:09, 2.52it/s] 26%|██▌ | 8/31 [00:03<00:09, 2.53it/s] 29%|██▉ | 9/31 [00:03<00:08, 2.48it/s] 32%|███▏ | 10/31 [00:03<00:08, 2.53it/s] 35%|███▌ | 11/31 [00:04<00:07, 2.52it/s] 39%|███▊ | 12/31 [00:04<00:07, 2.47it/s] 42%|████▏ | 13/31 [00:05<00:07, 2.49it/s] 45%|████▌ | 14/31 [00:05<00:06, 2.59it/s] 48%|████▊ | 15/31 [00:05<00:05, 2.72it/s] 52%|█████▏ | 16/31 [00:06<00:05, 2.77it/s] 55%|█████▍ | 17/31 [00:06<00:05, 2.72it/s] 58%|█████▊ | 18/31 [00:07<00:04, 2.64it/s] 61%|██████▏ | 19/31 [00:07<00:04, 2.64it/s] 65%|██████▍ | 20/31 [00:07<00:04, 2.66it/s] 68%|██████▊ | 21/31 [00:08<00:03, 2.65it/s] 71%|███████ | 22/31 [00:08<00:03, 2.59it/s] 74%|███████▍ | 23/31 [00:08<00:03, 2.64it/s] 77%|███████▋ | 24/31 [00:09<00:02, 2.70it/s] 81%|████████ | 25/31 [00:09<00:02, 2.58it/s] 84%|████████▍ | 26/31 [00:10<00:01, 2.75it/s] 87%|████████▋ | 27/31 [00:10<00:01, 2.89it/s] 90%|█████████ | 28/31 [00:10<00:01, 2.90it/s] 94%|█████████▎| 29/31 [00:10<00:00, 2.95it/s] 97%|█████████▋| 30/31 [00:11<00:00, 3.44it/s] 100%|██████████| 31/31 [00:11<00:00, 4.05it/s] 100%|██████████| 31/31 [00:11<00:00, 2.74it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s Finished.